CN112115554A - Control method and system for reducing collision damage of intelligent vehicle - Google Patents

Control method and system for reducing collision damage of intelligent vehicle Download PDF

Info

Publication number
CN112115554A
CN112115554A CN202011007668.0A CN202011007668A CN112115554A CN 112115554 A CN112115554 A CN 112115554A CN 202011007668 A CN202011007668 A CN 202011007668A CN 112115554 A CN112115554 A CN 112115554A
Authority
CN
China
Prior art keywords
vehicle
collision
model
determination system
damage
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011007668.0A
Other languages
Chinese (zh)
Other versions
CN112115554B (en
Inventor
秦也辰
黄义伟
伊赫桑·哈希米
阿米尔·卡杰普尔
王振峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN202011007668.0A priority Critical patent/CN112115554B/en
Publication of CN112115554A publication Critical patent/CN112115554A/en
Application granted granted Critical
Publication of CN112115554B publication Critical patent/CN112115554B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/25—Design optimisation, verification or simulation using particle-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation
    • B60W2050/0031—Mathematical model of the vehicle
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Abstract

The invention relates to a control method and a control system for reducing collision damage of an intelligent vehicle. The control method and the system for reducing the intelligent vehicle collision damage adopt a self-adaptive fuzzy neural network to organically fit the damage degree and the vehicle collision position to obtain a damage degree dynamic determination system, and then use an MPC (dynamic control protocol) planning-controller model constructed by a dynamic model as a control basis to construct a vehicle collision damage reduction model capable of reducing the collision damage degree, further adopt the vehicle collision damage reduction model to complete the control of the vehicle, so as to realize objective establishment of the relation between collision statistical data and vehicle dynamic control and achieve the purpose of reducing the collision damage degree based on the objective collision data.

Description

Control method and system for reducing collision damage of intelligent vehicle
Technical Field
The invention relates to the field of vehicle control, in particular to a control method and a control system for reducing collision damage of an intelligent vehicle.
Background
The automatic driving vehicle is the development direction of future vehicle technology, the decision and control realized based on perception are expected to reduce the probability of car accidents, and the injury to passengers can be effectively reduced when the car accidents happen.
Obstacle avoidance \ collision avoidance: the core concept of the prior art is "Time To Collision (TTC)". The time from the current moment to the collision can be calculated according to the speed and the course angle of the surrounding vehicles and the speed and the course angle of the vehicle. Based on the TTC and a predefined threshold, a corresponding control behavior may be set. Such as the existing adaptive cruise technology ACC, and the disclosures of patents CN201910266900.3, cn201680041015.x, CN201910187945.1, CN201910121503.7, etc.
And (3) impact damage is reduced: the existing impact damage reduction control modules are mostly connected in series behind the path planning module, namely when no feasible path exists, the existing impact damage reduction control modules are switched into the damage reduction module. Much consideration in the prior art is given to crash injury assessment and control prior to a crash, as disclosed in patents 201910982338.4, CN202010300349.2, CN202010088791.3 and CN201811354515.6, and how to perform dynamic control after a crash to reduce vehicle runaway, publication CN 202010115954.2. At present, in the aspect of vehicle collision injury research, the most extensive concept is Delta-V, the concept is obtained by momentum conservation calculation and is used for defining the speed difference value before and after vehicle collision, and the large speed difference value represents that the accident injury degree is high. However, the concept does not consider the collision position, and the actual vehicle collision damage has strong correlation with the vehicle collision position, so that the dynamic control of the reduction of the collision damage needs to be carried out on the basis of Delta-V by combining the collision position. In the paper, "h.wang, y.huang, a.khajepour, y.zhang, y.rasekhipour and d.cao," blast chemistry in Motion Planning for Autonomous Vehicles, "in IEEE Transactions on Intelligent transfer Systems, vol.20, No.9, pp.3313-3323," the authors discuss impact factors and construct therefrom a multi-objective weighting function aimed at reducing impact injuries. However, a plurality of vehicle factors are considered in the design, the construction of the objective function depends on subjective weight selection, and the dynamic behavior of the system is determined by the result of the subjective weight selection. The actual impact injury is objective, so the injury evaluation should be performed based on objective data and used for system control.
Therefore, based on the above, there is no disclosure in the prior art of a method or system for establishing a link between impact statistical data and vehicle dynamics control based on objective data, nor is there any disclosure of a control method or system that can achieve reduced impact injury based on such objective impact data.
Disclosure of Invention
The invention aims to provide a control method and a control system for reducing intelligent vehicle collision injury, which can objectively establish the relation between collision statistical data and vehicle dynamics control and reduce the degree of collision injury based on the objective collision data.
In order to achieve the purpose, the invention provides the following scheme:
a control method to reduce intelligent vehicle collision injuries, comprising:
acquiring a dynamic model of the vehicle; the kinetic model includes: the method comprises the following steps of (1) carrying out tire joint slip model, transverse and longitudinal dynamic models of a vehicle and a vehicle kinematic model;
constructing an MPC planning-controller model according to the dynamic model;
acquiring a relation curve between the injury degree of the vehicle and the collision position of the vehicle, and recording the relation curve as an MAIS3+ curve;
carrying out region division on the collision position of the vehicle to obtain a plurality of collision subareas;
acquiring a collision angle, Delta-V and MAIS3+ values in a plurality of collision subareas of a vehicle;
taking the collision angle and the Delta-V as input, taking the MAIS3+ value as output, and constructing an initial injury degree dynamic determination system by adopting a system modeling method;
training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a trained injury degree dynamic determination system;
constructing a damage model for reducing vehicle collision according to the MPC planning-controller model and the trained damage degree dynamic determination system;
and controlling the vehicle by adopting the model for reducing the vehicle collision damage so as to reduce the damage degree of the vehicle.
Preferably, the training of the initial injury degree dynamic determination system by using the adaptive fuzzy neural network to obtain a trained injury degree dynamic determination system specifically includes:
training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a first injury degree dynamic determination system;
using the formula CSI ═ a1·Δu3+a2·Δu·CD2+a3Fitting the first damage degree dynamic determination system to obtain a second damage degree dynamic determination system; the second damage degree dynamic determination system is a trained damage degree dynamic determination system;
in the formula, Deltau is Delta-V, a1,a2,a3Are fitting coefficients, and CD is the collision angle.
Preferably, the acquiring a dynamic model of the vehicle previously comprises:
acquiring wheel parameters and vehicle parameters of the vehicle; the wheel parameters comprise wheel radius, wheel rotating speed, wheel longitudinal force, torque applied by a single wheel and wheel rotational inertia; the vehicle parameters include a vehicle yaw rate and a vehicle lateral velocity;
building a lateral dynamics model of the vehicle and tires of the vehicle according to the wheel parameters;
constructing a vehicle kinematic model of the vehicle according to the wheel parameters and the vehicle parameters;
determining a kinetic model of the vehicle from the wheel parameters based on the lateral kinetic model of the tire and vehicle and the vehicle kinematic model.
Preferably, the performing region division on the collision position of the vehicle to obtain a plurality of collision sub-regions specifically includes:
the horizontal circumferential area of the vehicle is divided into four collision sub-areas by adopting two straight lines which are at specific angles and pass through the center of mass of the vehicle.
Preferably, the MPC planning-controller model is J:
Figure BDA0002696513090000041
in the formula, spIs the distance between the vehicle's centroid position and its proximate vehicle centroid position at time p, upIs the control input at time p and,
Figure BDA0002696513090000042
control input at time p-1, Q is the relative distance of the vehicle, H is the smoothness of the control input, M is the weight matrix of the control input, NpTo predict the time domain length.
Preferably, the model for reducing the vehicle collision damage is J3：
Figure BDA0002696513090000043
Wherein, CSI is collision damage degree upIs the control input at time p and,
Figure BDA0002696513090000044
control input at time p-1, Q is the relative distance of the vehicle, H is the smoothness of the control input, M is the weight matrix of the control input, NpTo predict the time domain length.
A control system to reduce intelligent vehicle collision injuries, comprising:
the dynamic model acquisition module is used for acquiring a dynamic model of the vehicle; the kinetic model includes: a lateral dynamics model of the tire and vehicle and a vehicle kinematics model;
the controller model building module is used for building an MPC planning-controller model according to the dynamic model;
the relation curve acquisition module is used for acquiring a relation curve between the injury degree of the vehicle and the collision position of the vehicle, and recording the relation curve as an MAIS3+ curve;
the collision region dividing module is used for carrying out region division on the collision position of the vehicle to obtain a plurality of collision sub-regions;
the data acquisition module is used for acquiring a collision angle, Delta-V and MAIS3+ values in a plurality of collision subareas of the vehicle;
the initial damage degree dynamic determination system building module is used for building an initial damage degree dynamic determination system by using a system building method with the collision angle and the Delta-V as input and the MAIS3+ value as output;
the injury degree dynamic determination system training module is used for training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a trained injury degree dynamic determination system;
the vehicle collision damage reduction model building module is used for building a vehicle collision damage reduction model according to the MPC planning-controller model and the trained damage degree dynamic determination system;
and the collision damage control module is used for adopting the vehicle collision damage reduction model to control the vehicle so as to reduce the damage degree of the vehicle.
Preferably, the system training module for dynamically determining the injury degree specifically includes:
the training unit is used for training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a first injury degree dynamic determination system;
a fitting unit for applying the formula CSI ═ a1·Δu3+a2·Δu·CD2+a3Fitting the first damage degree dynamic determination system to obtain a second damage degree dynamic determination system; the second damage degree dynamic determination system is a trained damage degree dynamic determination system;
in the formula, Deltau is Delta-V, a1,a2,a3Are fitting coefficients, and CD is the collision angle.
Preferably, the control system further includes:
the parameter acquisition module is used for acquiring wheel parameters and vehicle parameters of the vehicle; the wheel parameters comprise wheel radius, wheel rotating speed, wheel longitudinal force, torque applied by a single wheel and wheel rotational inertia; the vehicle parameters include a vehicle yaw rate and a vehicle lateral velocity;
a lateral dynamics model construction module for constructing a lateral dynamics model of the vehicle and the tires of the vehicle according to the wheel parameters;
the kinematic model building module is used for building the vehicle kinematic model according to the wheel parameters and the vehicle parameters;
a dynamic model building module for determining a dynamic model of the vehicle from the wheel parameters based on the lateral dynamic model of the tire and vehicle and the vehicle kinematic model.
Preferably, the collision region dividing module specifically includes:
and the collision region dividing unit is used for dividing the horizontal circumferential region of the vehicle into four collision subareas by adopting two straight lines which are at specific angles and pass through the mass center of the vehicle.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a control method and a control system for reducing intelligent vehicle collision injury, which adopt a self-adaptive fuzzy neural network to organically fit the injury degree and a vehicle collision position to obtain an injury degree dynamic determination system, and then construct a vehicle collision injury reduction model capable of reducing the collision injury degree by taking an MPC (multi-control processor) planning-controller model constructed by a dynamic model as a control basis, and further adopt the vehicle collision injury reduction model to complete vehicle control, so as to realize objective establishment of relation between collision statistical data and vehicle dynamics control and the purpose of reducing the collision injury degree based on the objective collision data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a control method for reducing intelligent vehicle collision injuries provided by the present invention;
FIG. 2 is a schematic diagram of a position structure of four collision sub-regions in an embodiment of the present invention;
FIG. 3 is a graph of a function fitting Delta-V to a collision mode in the prior art document;
FIG. 4 is a diagram of an ANFIS mapping relationship obtained by CSI calculation according to an embodiment of the present invention;
FIG. 5 is a diagram of a dynamic model of a vehicle according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a control system for reducing collision damage of an intelligent vehicle provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a control method and a control system for reducing intelligent vehicle collision injury, so that the relation between collision statistical data and vehicle dynamics control can be objectively established, and the degree of collision injury can be reduced based on the objective collision data.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flowchart of a control method for reducing an intelligent vehicle collision injury provided by the present invention, and as shown in fig. 1, a control method for reducing an intelligent vehicle collision injury includes:
step 100: a dynamic model of the vehicle is obtained. The dynamic model comprises: a lateral dynamics model of the tire with the vehicle and a vehicle kinematics model.
Step 101: and constructing an MPC planning-controller model according to the dynamic model. The MPC plan-controller model is preferably J:
Figure BDA0002696513090000071
in the formula, spIs the distance between the vehicle's centroid position and its proximate vehicle centroid position at time p, upIs the control input at time p and,
Figure BDA0002696513090000072
control input at time p-1, Q is the relative distance of the vehicle, H is the smoothness of the control input, M is the weight matrix of the control input, NpTo predict the time domain length.
Further based on the MPC planning-controller model constructed above, in the present invention, the MPC problem can be summarized as follows:
subject to
Figure BDA0002696513090000073
wherein u is*For the calculated control input, the constraints include system state constraints, upper and lower limits for the control input, and system state stability domain constraints. Solving the MPC problem can obtain the system input at the current time.
According to the MPC planning-controller model, the MPC planning-controller can realize the maximization of the distance between the MPC planning-controller and the similar vehicle by adjusting the output of the system actuator under the premise of considering the system input and the dynamic constraint, thereby completing the synchronous realization of path planning and path tracking. It can be seen that compared with the current path planning and path tracking relatively independent method, the proposed algorithm can complete the synchronous control of planning and tracking control only by one controller.
Step 102: and acquiring a relation curve between the damage degree of the vehicle and the collision position of the vehicle, and recording the relation curve as an MAIS3+ curve.
Step 103: and carrying out region division on the collision position of the vehicle to obtain a plurality of collision subareas. In the present invention, step 103 preferably divides the horizontal circumferential area of the vehicle into four collision sub-areas using two straight lines at specific angles and each passing through the center of mass of the vehicle. A schematic diagram of the divided regions of the four collision sub-regions is shown in fig. 2.
Step 104: the collision angle of the vehicle, Delta-V and MAIS3+ values in multiple collision sub-zones are obtained.
Step 105: and (3) taking the collision angle and Delta-V as input, taking the MAIS3+ value as output, and constructing an initial injury degree dynamic determination system by adopting a system modeling method.
Step 106: and training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a trained injury degree dynamic determination system.
The method specifically comprises the following steps:
and training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a first injury degree dynamic determination system.
Using the formula CSI ═ a1·Δu3+a2·Δu·CD2+a3And fitting the first damage degree dynamic determination system to obtain a second damage degree dynamic determination system. The second damage degree dynamic determination system is a trained damage degree dynamic determination system.
In the formula, Deltau is Delta-V, a1,a2,a3Are fitting coefficients, and CD is the collision angle.
Step 107: and constructing a damage model for reducing vehicle collision according to the MPC planning-controller model and the trained damage degree dynamic determination system. The model for reducing vehicle collision damage is preferably J3：
Figure BDA0002696513090000091
Wherein, CSI is collision damage degree upIs the control input at time p and,
Figure BDA0002696513090000092
control input at time p-1, Q is the relative distance of the vehicle, H is the smoothness of the control input, M is the weight matrix of the control input, NpTo predict the time domain length.
Step 108: and controlling the vehicle by adopting a vehicle collision damage reduction model to reduce the damage degree of the vehicle.
The key to constructing the reduced vehicle collision damage model in step 107 above is to accurately obtain the impact severity metric function CSI. The determination method of the CSI is not exclusive, and the present invention proposes a way to determine the CSI based on Delta-V and the collision location and integrate the calculated CSI into the damage reduction control.
In The field of crash safety, The literature (l.greenspan, b.a.mclellan, and h.greig, "abbrevated injure scale and injure safety score: a scientific chart." The Journal word of, vol.25, No.1, pp.60-64, 1985.) defines The injury rating MAIS3+ (maximum injury assessment index equal to or greater than 3), as severe injuries and fits their injury probability as a function of Delta-V and crash mode (fig. 3), but this curve is fitted from a large amount of car accident data, and The difference in data samples may cause The car accident injury curve to change.
In addition, although the function establishes the relationship between the damage degree and the vehicle collision position, the function is difficult to be embedded into a design control algorithm for overall control due to four discrete curves. And because the discontinuous non-derivable function cannot be directly applied to the MPC objective function (and other control algorithms cannot control with the discrete objective function), the vehicle control cannot be performed based on the objective data. Therefore, there is a need to provide a universal method capable of transforming any traffic accident damage curve and applying the same to vehicle control.
The method for determining the CSI provided by the invention does not depend on specific traffic accident data, has universality and can improve accuracy, and is mainly directly applied to an MPC objective function through the conversion between an MAIS3+ curve and the objective function so as to realize the control of reducing the damage degree of a vehicle. Wherein, the detailed conversion process between the MAIS3+ curve and the objective function is as follows:
step 1: according to fig. 2, the vehicle-cycle range [0 °,360 ° ] is divided into four impact sub-regions (set to the starting 0 ° from the front left front side, the above angle being the impact angle CD): the first collisional subregion is the region between 0, 40 of the frontal extent. The second collisional sub-region is the region between the distal extents [40 °,180 ° ]. The third impingement sub-region is the region between the rear range [220 °,360 ° ]. The fourth collisional sub-region is the region between the proximal extents [220 °,360 ° ].
To achieve the application of the MAIS3+ curve, the four discrete curves in FIG. 3 are first converted to continuous variables. Random numbers are generated in the range of [0 degrees and 360 degrees ], and according to the four collision subregions and the corresponding MAIS3+ values defined above, a damage degree dynamic determination system (initial damage degree dynamic determination system) with a collision angle and Delta-V as inputs and an MAIS3+ value (CSI) as an output can be constructed. The method for constructing the damage degree dynamic determination system is various, and any system modeling method can be adopted. The modeling method is exemplified as the ANFIS method in the invention, and the method is not exclusive.
Step 2: and continuously describing the damage degree dynamic determination system constructed by the above steps. Here, an adaptive fuzzy neural network (ANFIS) is used to train the constructed injury dynamic determination system (the input is the impingement angle, Delta-V, and the output is mais. the method is not unique), and a continuous fuzzy surface can be obtained, as shown in fig. 4. As can be seen in fig. 4, the discrete function of fig. 3 has been transformed into the continuous function of fig. 4.
And step 3: the continuously-derivable function (initial injury level dynamic determination system) of figure 4 has been applied to the MPC planning-controller model constructed above. However, the ANFIS model used is a system model (i.e., a plurality of first-order TS linear functions) mapped by a plurality of fuzzy rules, which may cause difficulty in MPC application. Therefore, the continuous curved surface (the continuous curved surface shown in fig. 4 obtained by the continuous derivative function) may be continuously fitted for the second time, and the curved surface may be expressed in a polynomial form, so as to obtain the trained dynamic injury determination system.
Among them, the present invention preferably adopts the following function to perform quadratic fitting on the initial injury degree dynamic determination system (continuous derivative function):
CSI＝a1·Δu3+a2·Δu·CD2+a3。
wherein, Delta u is Delta-V, a1,a2,a3For the fitting coefficients, CD is the impingement angle.
Fitting coefficient a1,a2,a3The identification of (a) is obtained by a particle swarm optimization algorithm (PSO). Since the PSO method is one of the identification methods and is a known technique, it is not discussed in detail in the present invention. Further, the method of identifying the parameter is not limited to the only method, and a least square method or the like may be used.
The identification input is two independent variables of Delta-V and CD, the output is CSI, and the training is directly carried out. In the training process, the formula CSI ═ a is mainly adopted1·Δu3+a2·Δu·CD2+a3To approximate the surface of fig. 4, the formula contains several parameters to be identified. After the parameters are identified, the CSI can be approximated. Can be understood as the formula CSI ═ a1·Δu3+a2·Δu·CD2+a3Is an approximate mathematical analytic representation of fig. 4, the present invention uses PSO to minimize the error between this representation and the actual value.
After obtaining this CSI, the obtained CSI is directly substituted for s in the MPC planning-controller modelpAnd obtaining the model for reducing the vehicle collision damage.
Preferably, before acquiring the dynamic model of the vehicle, the method further includes: the process of constructing the dynamic surface model specifically comprises the following steps:
wheel parameters of the vehicle and vehicle parameters are obtained. The wheel parameters include wheel radius, wheel speed, wheel longitudinal force, torque applied by a single wheel, and wheel moment of inertia. The vehicle parameters include vehicle yaw rate and vehicle lateral velocity.
A tire and vehicle lateral dynamics model of the vehicle is constructed from the wheel parameters.
And constructing a vehicle kinematic model of the vehicle according to the wheel parameters and the vehicle parameters.
The dynamic model of the vehicle is determined from the wheel parameters on the basis of the lateral dynamic models of the tyre and of the vehicle and of the kinematic model of the vehicle.
In practical implementation, the above dynamic model construction process can be further refined as follows:
as shown in fig. 5, the dynamic model of each wheel can be described by the following equation:
Figure BDA0002696513090000121
wherein the content of the first and second substances,
Figure BDA0002696513090000122
longitudinal acceleration mapped for each angle (at the tire), IωFor the moment of inertia of the tyre, TijFor the total torque on each tire, uijIs the speed of the vehicle centroid velocity mapped to the wheel, i F/R (front and rear wheels), j L/R (left and right wheels), ur＝Rω-utR is the wheel radius, omega is the wheel speed, utIs the wheel longitudinal speed. u. ofijIn order to map to the longitudinal acceleration of the wheel,
Figure BDA0002696513090000127
for wheel longitudinal forces, TijThe torque applied for a single wheel, IωIs the moment of inertia of the wheel. Note: the wheel force can be generated by any tire mechanical model, so that the complex dynamic behavior of the tire can be accurately described.
A vehicle dynamics model is established, and the yaw rate r and the lateral velocity v can be expressed as follows:
Figure BDA0002696513090000123
Figure BDA0002696513090000124
wherein the content of the first and second substances,
Figure BDA0002696513090000125
indicating the longitudinal (lateral) force at the front (rear) wheels,
Figure BDA0002696513090000126
showing the difference (f) of the tire forces on both sides of the longitudinal (transverse) direction of the front (rear) axlexIn the longitudinal direction of the front wheel, fyIs the front wheel transverse direction, rxLongitudinal direction of rear wheel, ryThe rear wheel lateral). Unlike existing path planning and path tracking algorithms, the proposed algorithm further considers the coordinates of the vehicle in the geodetic coordinate system:
Figure BDA0002696513090000131
Figure BDA0002696513090000132
wherein the content of the first and second substances,
Figure BDA0002696513090000133
the coordinates X and Y of the mass center of the vehicle under the geodetic coordinate system are shown, u is the longitudinal speed of the vehicle, v is the transverse speed of the vehicle, and psi is the heading angle of the vehicle. To facilitate controller implementation and to solve real-time problems, it can be locally linearized.
On the basis, the expression of the vehicle system planning/tracking integrated state space is listed as follows:
Figure BDA0002696513090000134
wherein the content of the first and second substances,
Figure BDA0002696513090000135
Figure BDA0002696513090000136
to illustrate the algorithm, the system control inputs are selected as the front wheel steering angle and the control torque u at the four wheels ═ Tfl Tfr Trl Trr]But not limited thereto, different combinations of control inputs may be used to achieve the same goal.
The system state is chosen as x ═ v r τf τr ur X Y ψ]I.e., vehicle lateral velocity, yaw rate, wheel slip angle, relative speed at the wheels, vehicle generalized coordinates, and vehicle heading angle.
The system outputs are vehicle yaw angle, yaw rate and vehicle generalized coordinates.
Figure BDA0002696513090000143
The system is in an uncontrolled input state.
The core of the path planning and tracking integrated algorithm introduced by the invention depends on taking the generalized coordinates of the vehicle into the system state and controlling the generalized coordinates. Although this idea is mentioned in (h.wang, y.huang, a.khajepour, y.zhang, y.rasekhipour and d.cao, "blast chemistry in Motion Planning for Autonomous Vehicles," in IEEE Transactions on Intelligent transmission Systems, vol.20, No.9, pp.3313-3323), the problem of coupling between states needs to be solved since the vehicle generalized coordinates depend on the vehicle longitudinal speed, but the above-mentioned article does not solve this problem (i.e. the paper state variables include the longitudinal speed, while other states are coupled to the longitudinal speed in the state matrix). According to the invention, the complete decoupling of the system state is realized by constructing the wheel cornering angle variable and the wheel relative speed and locally linearizing the generalized coordinates of the vehicle.
To achieve system control, the system is further discretized into:
Figure BDA0002696513090000141
Figure BDA0002696513090000142
where the subscript d is a discrete representation of the corresponding letter, and k represents the discrete time k instant.
In addition, corresponding to the control method for reducing the collision damage of the intelligent vehicle, the invention also correspondingly provides a control system for reducing the collision damage of the intelligent vehicle, as shown in fig. 6, the control system comprises:
the dynamic model obtaining module 1 is used for obtaining a dynamic model of the vehicle. The dynamic model comprises: a lateral dynamics model of the tire with the vehicle and a vehicle kinematics model.
And the controller model building module 2 is used for building an MPC planning-controller model according to the dynamic model.
And the relation curve acquisition module 3 is used for acquiring a relation curve between the injury degree of the vehicle and the collision position of the vehicle, and the relation curve is recorded as an MAIS3+ curve.
And the collision region dividing module 4 is used for performing region division on the collision position of the vehicle to obtain a plurality of collision sub-regions.
And the data acquisition module 5 is used for acquiring Delta-V of the vehicle and MAIS3+ values in a plurality of collision subareas.
And the initial injury degree dynamic determination system building module 6 is used for building an initial injury degree dynamic determination system by using a system modeling method and taking the collision angle and Delta-V as inputs and the MAIS3+ value as an output.
And the damage degree dynamic determination system training module 7 is used for training the initial damage degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a trained damage degree dynamic determination system.
And the vehicle collision damage reduction model building module 8 is used for building a vehicle collision damage reduction model according to the MPC planning-controller model and the trained damage degree dynamic determination system.
And the collision damage control module 9 is used for controlling the vehicle by adopting the vehicle collision damage reduction model so as to reduce the damage degree of the vehicle.
As a preferred embodiment of the present invention, the system training module 7 for dynamically determining a degree of injury specifically includes:
and the training unit is used for training the initial injury degree dynamic determination system by adopting the self-adaptive fuzzy neural network to obtain a first injury degree dynamic determination system.
A fitting unit for applying the formula CSI ═ a1·Δu3+a2·Δu·CD2+a3And fitting the first damage degree dynamic determination system to obtain a second damage degree dynamic determination system. The second damage degree dynamic determination system is a trained damage degree dynamic determination system.
In the formula, Deltau is Delta-V, a1,a2,a3Are fitting coefficients, CD is bumpThe angle of impact.
As another preferred embodiment of the present invention, the control system further includes:
the parameter acquisition module is used for acquiring wheel parameters of the vehicle and vehicle parameters. The wheel parameters include wheel radius, wheel speed, wheel longitudinal force, torque applied by a single wheel, and wheel moment of inertia. The vehicle parameters include vehicle yaw rate and vehicle lateral velocity.
And the transverse dynamic model building module is used for building a tire of the vehicle and a transverse dynamic model of the vehicle according to the wheel parameters.
And the kinematic model building module is used for building a vehicle kinematic model according to the wheel parameters and the vehicle parameters.
And the dynamic model building module is used for determining the dynamic model of the vehicle according to the wheel parameters based on the lateral dynamic models of the tire and the vehicle kinematic model.
As another preferred embodiment of the present invention, the collision region dividing module 4 specifically includes:
and the collision region dividing unit is used for dividing the horizontal circumferential region of the vehicle into four collision subareas by adopting two straight lines which are at specific angles and pass through the center of mass of the vehicle.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims (10)

1. A control method for reducing intelligent vehicle collision injuries is characterized by comprising the following steps:
acquiring a dynamic model of the vehicle; the kinetic model includes: a lateral dynamics model of the tire and vehicle and a vehicle kinematics model;
constructing an MPC planning-controller model according to the dynamic model;
acquiring a relation curve between the injury degree of the vehicle and the collision position of the vehicle, and recording the relation curve as an MAIS3+ curve;
carrying out region division on the collision position of the vehicle to obtain a plurality of collision subareas;
acquiring a collision angle, Delta-V and MAIS3+ values in a plurality of collision subareas of a vehicle;
taking the collision angle and the Delta-V as input, taking the MAIS3+ value as output, and constructing an initial injury degree dynamic determination system by adopting a system modeling method;
training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a trained injury degree dynamic determination system;
constructing a damage model for reducing vehicle collision according to the MPC planning-controller model and the trained damage degree dynamic determination system;
and controlling the vehicle by adopting the model for reducing the vehicle collision damage so as to reduce the damage degree of the vehicle.
2. The control method for reducing the collision damage of the intelligent vehicle according to claim 1, wherein the training of the initial damage degree dynamic determination system by using the adaptive fuzzy neural network to obtain the trained damage degree dynamic determination system specifically comprises:
training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a first injury degree dynamic determination system;
using the formula CSI ═ a1·Δu3+a2·Δu·CD2+a3Fitting the first damage degree dynamic determination system to obtain a second damage degree dynamic determination system; the second damage degree dynamic determination system is a trained damage degree dynamic determination system;
in the formula, Deltau is Delta-V, a1,a2,a3Are fitting coefficients, and CD is the collision angle.
3. The control method for reducing intelligent vehicle collision damage according to claim 1, wherein the obtaining of the dynamic model of the vehicle previously comprises:
acquiring wheel parameters and vehicle parameters of the vehicle; the wheel parameters comprise wheel radius, wheel rotating speed, wheel longitudinal force, torque applied by a single wheel and wheel rotational inertia; the vehicle parameters include a vehicle yaw rate and a vehicle lateral velocity;
building a lateral dynamics model of the vehicle and tires of the vehicle according to the wheel parameters;
constructing a vehicle kinematic model of the vehicle according to the wheel parameters and the vehicle parameters;
determining a kinetic model of the vehicle from the wheel parameters based on the lateral kinetic model of the tire and vehicle and the vehicle kinematic model.
4. The control method for reducing the collision damage of the intelligent vehicle according to claim 1, wherein the step of performing region division on the collision position of the vehicle to obtain a plurality of collision sub-regions specifically comprises:
the horizontal circumferential area of the vehicle is divided into four collision sub-areas by adopting two straight lines which are at specific angles and pass through the center of mass of the vehicle.
5. The control method for reducing intelligent vehicle collision injuries of claim 1, wherein the MPC planning-controller model is J:
Figure FDA0002696513080000021
in the formula, spIs the distance between the vehicle's centroid position and its proximate vehicle centroid position at time p, upIs the control input at time p and,
Figure FDA0002696513080000022
control input at time p-1, Q is the relative distance of the vehicle, H is the smoothness of the control input, M is the weight matrix of the control input, NpTo predict the time domain length.
6. The control method for reducing the collision damage of the intelligent vehicle as claimed in claim 1, wherein the model for reducing the collision damage of the vehicle is J3：
Figure FDA0002696513080000031
Wherein, CSI is collision damage degree upIs the control input at time p and,
Figure FDA0002696513080000032
control input at time p-1, Q is the relative distance of the vehicle, H is the smoothness of the control input, M is the weight matrix of the control input, NpTo predict the time domain length.
7. A control system for reducing intelligent vehicle collision injuries, comprising:
the dynamic model acquisition module is used for acquiring a dynamic model of the vehicle; the kinetic model includes: a lateral dynamics model of the tire and vehicle and a vehicle kinematics model;
the controller model building module is used for building an MPC planning-controller model according to the dynamic model;
the relation curve acquisition module is used for acquiring a relation curve between the injury degree of the vehicle and the collision position of the vehicle, and recording the relation curve as an MAIS3+ curve;
the collision region dividing module is used for carrying out region division on the collision position of the vehicle to obtain a plurality of collision sub-regions;
the data acquisition module is used for acquiring a collision angle, Delta-V and MAIS3+ values in a plurality of collision subareas of the vehicle;
the initial damage degree dynamic determination system building module is used for building an initial damage degree dynamic determination system by using a system building method with the collision angle and the Delta-V as input and the MAIS3+ value as output;
the injury degree dynamic determination system training module is used for training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a trained injury degree dynamic determination system;
the vehicle collision damage reduction model building module is used for building a vehicle collision damage reduction model according to the MPC planning-controller model and the trained damage degree dynamic determination system;
and the collision damage control module is used for adopting the vehicle collision damage reduction model to control the vehicle so as to reduce the damage degree of the vehicle.
8. The control system for reducing the collision damage of the intelligent vehicle according to claim 7, wherein the damage degree dynamic determination system training module specifically comprises:
the training unit is used for training the initial injury degree dynamic determination system by adopting a self-adaptive fuzzy neural network to obtain a first injury degree dynamic determination system;
a fitting unit for applying the formula CSI ═ a1·Δu3+a2·Δu·CD2+a3Fitting the first damage degree dynamic determination system to obtain a second damage degree dynamic determination system; the second damage degree dynamic determination system is a trained damage degree dynamic determination system;
in the formula, Deltau is Delta-V, a1,a2,a3Are fitting coefficients, and CD is the collision angle.
9. The control system for reducing intelligent vehicle collision injuries of claim 7, further comprising:
the parameter acquisition module is used for acquiring wheel parameters and vehicle parameters of the vehicle; the wheel parameters comprise wheel radius, wheel rotating speed, wheel longitudinal force, torque applied by a single wheel and wheel rotational inertia; the vehicle parameters include a vehicle yaw rate and a vehicle lateral velocity;
a lateral dynamics model construction module for constructing a lateral dynamics model of the vehicle and the tires of the vehicle according to the wheel parameters;
the kinematic model building module is used for building the vehicle kinematic model according to the wheel parameters and the vehicle parameters;
a dynamic model building module for determining a dynamic model of the vehicle from the wheel parameters based on the lateral dynamic model of the tire and vehicle and the vehicle kinematic model.
10. The control system for reducing the collision damage of the intelligent vehicle according to claim 7, wherein the collision area dividing module specifically comprises:
and the collision region dividing unit is used for dividing the horizontal circumferential region of the vehicle into four collision subareas by adopting two straight lines which are at specific angles and pass through the mass center of the vehicle.
CN202011007668.0A 2020-09-23 2020-09-23 Control method and system for reducing collision damage of intelligent vehicle Active CN112115554B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011007668.0A CN112115554B (en) 2020-09-23 2020-09-23 Control method and system for reducing collision damage of intelligent vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011007668.0A CN112115554B (en) 2020-09-23 2020-09-23 Control method and system for reducing collision damage of intelligent vehicle

Publications (2)

Publication Number Publication Date
CN112115554A true CN112115554A (en) 2020-12-22
CN112115554B CN112115554B (en) 2022-10-11

Family

ID=73801510

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011007668.0A Active CN112115554B (en) 2020-09-23 2020-09-23 Control method and system for reducing collision damage of intelligent vehicle

Country Status (1)

Country Link
CN (1) CN112115554B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113401138A (en) * 2021-06-18 2021-09-17 清华大学 Method, device and system for calculating potential collision severity index

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102167005A (en) * 2011-04-08 2011-08-31 清华大学 Method for judging and acting before automobile collision to reduce collision loss
CN110027553A (en) * 2019-04-10 2019-07-19 湖南大学 A kind of anti-collision control method based on deeply study
CN110481543A (en) * 2019-08-22 2019-11-22 宝能汽车有限公司 A kind of method and device for coping with vehicle running collision
JP2020061088A (en) * 2018-10-12 2020-04-16 一般財団法人日本自動車研究所 Collision injury prediction model creation method, collision injury prediction method, collision injury prediction system, and advanced automatic accident notification system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102167005A (en) * 2011-04-08 2011-08-31 清华大学 Method for judging and acting before automobile collision to reduce collision loss
JP2020061088A (en) * 2018-10-12 2020-04-16 一般財団法人日本自動車研究所 Collision injury prediction model creation method, collision injury prediction method, collision injury prediction system, and advanced automatic accident notification system
CN110027553A (en) * 2019-04-10 2019-07-19 湖南大学 A kind of anti-collision control method based on deeply study
CN110481543A (en) * 2019-08-22 2019-11-22 宝能汽车有限公司 A kind of method and device for coping with vehicle running collision

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
CUI Q等: "A new strategy for rear-end collision avoidance via autonomous steering and differential braking in highway driving", 《VEHICLE SYSTEM DYNAMICS》 *
JI J等: "Path planning and tracking for vehicle collision avoidance based on model predictive control with multiconstraints", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》 *
PARSEH M等: "Pre-crash vehicle control and manoeuvre planning: A step towards minimizing collision severity for highly automated vehicles", 《2019 IEEE INTERNATIONAL CONFERENCE ON VEHICULAR ELECTRONICS AND SAFETY (ICVES)》 *
TSIOTRAS P等: "Real-time near-optimal feedback control of aggressive vehicle maneuvers", 《OPTIMIZATION AND OPTIMAL CONTROL IN AUTOMOTIVE SYSTEMS》 *
WANG H等: "Crash mitigation in motion planning for autonomous vehicles", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113401138A (en) * 2021-06-18 2021-09-17 清华大学 Method, device and system for calculating potential collision severity index
CN113401138B (en) * 2021-06-18 2022-05-03 清华大学 Method, device and system for calculating potential collision severity index

Also Published As

Publication number Publication date
CN112115554B (en) 2022-10-11

Similar Documents

Publication Publication Date Title
CN112068445B (en) Integrated control method and system for path planning and path tracking of automatic driving vehicle
CN109131312B (en) ACC/ESC integrated control system and method for intelligent electric vehicle
Lee et al. Lane-keeping assistance control algorithm using differential braking to prevent unintended lane departures
JP4143104B2 (en) Vehicle control device
US7996130B2 (en) Driver workload-based vehicle stability enhancement system
CN110286681B (en) Dynamic automatic driving track-changing planning method for curvature-variable curve
CN108773376B (en) Automobile multi-target layered cooperative control and optimization method fusing driving intentions
Dahmani et al. Observer-based robust control of vehicle dynamics for rollover mitigation in critical situations
CN106114511A (en) A kind of automobile cruise system core target identification method
JP2009051430A (en) Running support system
CN108569336A (en) Vehicle kinematics model rotating direction control method is based under Dynamic Constraints
CN112092805B (en) Integrated control method and system for collision avoidance and collision damage reduction of intelligent vehicle
CN110716562A (en) Decision-making method for multi-lane driving of unmanned vehicle based on reinforcement learning
Ahmed et al. Vehicle yaw rate control for lane change maneuver using fuzzy PID controller and neural network controller
Zhang et al. Real-time nonlinear predictive controller design for drive-by-wire vehicle lateral stability with dynamic boundary conditions
CN112115554B (en) Control method and system for reducing collision damage of intelligent vehicle
CN115542813A (en) Unmanned vehicle control method, device, electronic equipment and storage medium
Smith et al. Nonlinear-gain-optimised controller development and evaluation for automated emergency vehicle steering
Yue et al. Automated hazard escaping trajectory planning/tracking control framework for vehicles subject to tire blowout on expressway
Abdullah et al. Study the influence of distance in artificial potential field (APF) for autonomous emergency braking system (AEB) on longitudinal motion
Hakima et al. Designing a fuzzy logic controller to adjust the angle of tires in four wheel steering vehicles
CN115042770A (en) Vehicle queue transverse control method based on distributed robust model prediction
CN114834263A (en) Coordination control method and device for steering and torque vector of active front wheel of electric automobile
CN115048715A (en) Path planning and control algorithm of unmanned formula car
CN113327457A (en) Vehicle collision avoidance system and method based on vehicle-road cooperation technology

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant